Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/microsoft/managed-apps/create-appnpx skills add microsoft/managed-apps --skill create-appgit clone --depth 1 https://github.com/microsoft/managed-appsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00036 | $0.04480 |
| Opus 5 | $0.00018 | $0.02240 |
| Sonnet 5 | $0.00007 | $0.00896 |
| Haiku 4.5 | $0.00004 | $0.00448 |
Grade A, and why
create-app scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📋 Shared Instructions: shared-instructions.md — Cross-cutting concerns.
References:
- prerequisites-reference.md — Node, git, CLI install, allowedPrompts.
- troubleshooting.md — First-run Git Credential Manager trap, common
ms app createfailures.
Create a Microsoft App
This skill scaffolds a new Microsoft App end-to-end using @microsoft/managed-apps-cli (binary ms). The default outcome is a running local dev server, not a deployed cloud app. Deploying is a separate, explicit user choice via /deploy.
Workflow
- Memory Bank → 2. Prerequisites → 3. Gather Requirements → 4. Plan → 5. Auth → 6. Environment → 7. Scaffold → 8. Add Data Sources → 9. Implement App → 10. Local Dev → 11. Summary → 12. Memory Bank Update
Critical principle: when this skill ends and the user opens the local URL, they must see a functional app — connectors wired, screens implemented per the approved plan — not a bare template. Adding data sources and implementing the UI happen inside this skill, before ms app dev is started. Do not defer them to "next steps."
Step 1: Check Memory Bank
Check for memory-bank.md per shared-instructions.md. If found, ask the user whether they want to resume (e.g., re-run ms app dev against an existing scaffold) or start a new app.
Step 2: Validate Prerequisites
Run prerequisite checks first — no point gathering requirements if the environment isn't ready. Full details in prerequisites-reference.md.
The commands below are shown in bash syntax. If you are running PowerShell on Windows, use the equivalents described in shared-instructions.md and the PowerShell example in prerequisites-reference.md instead of copying the bash snippets literally.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 321 lines · 36 tokens per session scan A d1be52d261ef
create-app is a skill published in the GitHub repository microsoft/managed-apps (5 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 4,480 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…